文本向量调用参考_大模型服务平台百炼-阿里云帮助中心

功能描述

本文主要介绍如何使用SDK将文本数据快速转换为高质量的向量数据。

说明

请参考文档安装SDK, 安装对应编程语言的SDK。

调用说明

调用示例中的ACCESS_KEY_ID、ACCESS_KEY_SECRET、AGENT_KEY和APP_ID从系统环境变量中获取。执行示例前，请确保已正确设置相关的变量，或者在代码中直接修改变量。比如：

Java

String accessKeyId = "abc******123";
String accessKeySecret = "abd******124";
String agentKey = "abe******125";

Python

access_key_id = "abc******123"
access_key_secret = "abd******124"
agent_key = "abe******125"

accessKeyId = "abc******123"
accessKeySecret = "abd******124"
agentKey = "abe******125"

调用示例（文本向量）

Java

import com.aliyun.bailian20230601.Client;
import com.aliyun.bailian20230601.models.CreateTextEmbeddingsRequest;
import com.aliyun.bailian20230601.models.CreateTextEmbeddingsResponse;
import com.aliyun.bailian20230601.models.CreateTextEmbeddingsResponseBody;
import com.aliyun.broadscope.bailian.sdk.consts.ConfigConsts;
import com.aliyun.broadscope.bailian.sdk.consts.EmbeddingTextTypeEnum;
import com.aliyun.teaopenapi.models.Config;

import java.util.ArrayList;
import java.util.List;

public class TextEmbeddingTest {
    public void testCreateTextEmbeddings() {
        String accessKeyId = System.getenv("ACCESS_KEY_ID");
        String accessKeySecret = System.getenv("ACCESS_KEY_SECRET");
        String agentKey = System.getenv("AGENT_KEY");

        Config config = new Config()
                .setAccessKeyId(accessKeyId)
                .setAccessKeySecret(accessKeySecret)
                .setEndpoint(ConfigConsts.POP_ENDPOINT);

        try {
            Client client = new Client(config);

            List<String> input = new ArrayList<>();
            input.add("今天天气怎么样");

            CreateTextEmbeddingsRequest request = new CreateTextEmbeddingsRequest()
                    .setAgentKey(agentKey)
                    .setInput(input)
                    .setTextType(EmbeddingTextTypeEnum.DOCUMENT.getType());

            CreateTextEmbeddingsResponse response = client.createTextEmbeddings(request);
            CreateTextEmbeddingsResponseBody body = response.getBody();
            if (body == null || !body.success) {
                String error = body == null ? "create token error" : body.message;
                throw new BaiLianSdkException(error);
            }

            CreateTextEmbeddingsResponseBody.CreateTextEmbeddingsResponseBodyData data = body.getData();
            List<CreateTextEmbeddingsResponseBody.CreateTextEmbeddingsResponseBodyDataEmbeddings> embeddings = data.getEmbeddings();
            for (CreateTextEmbeddingsResponseBody.CreateTextEmbeddingsResponseBodyDataEmbeddings embedding : embeddings) {
                Integer textIndex = embedding.getTextIndex();
                List<Double> embeddingsArray = embedding.getEmbedding();

                System.out.printf("textIndex: %d, embedding: %s\n", textIndex, embeddingsArray);
            }
        } catch (BaiLianSdkException e) {
            throw e;
        } catch (Exception e) {
            throw new BaiLianSdkException(e);
        }
    }
}

Python

import os

from alibabacloud_bailian20230601.client import Client
from alibabacloud_bailian20230601.models import CreateTextEmbeddingsRequest
from alibabacloud_tea_openapi.models import Config

import broadscope_bailian


class TextEmbeddingTest():
    def test_create_embeddings(self):
        access_key_id = os.environ.get("ACCESS_KEY_ID")
        access_key_secret = os.environ.get("ACCESS_KEY_SECRET")
        agent_key = os.environ.get("AGENT_KEY")

        config = Config(access_key_id=access_key_id,
                        access_key_secret=access_key_secret,
                        endpoint=broadscope_bailian.pop_endpoint)

        client = Client(config=config)

        request = CreateTextEmbeddingsRequest(agent_key=agent_key,
                                              input=["今天天气怎么样", "我想去北京"],
                                              text_type="query")
        response = client.create_text_embeddings(request=request)
        if response.status_code != 200 or response.body is None:
            raise RuntimeError("create token error, code=%d" % response.status_code)

        body = response.body
        if not body.success:
            raise RuntimeError("create token error, code=%s, message=%s" % (body.code, body.message))

        for embedding in body.data.embeddings:
            print("index: %s, embeddings: %s\n" % (embedding.text_index, embedding.embedding))

import (
	"fmt"
	apiClient "github.com/alibabacloud-go/bailian-20230601/client"
	openapi "github.com/alibabacloud-go/darabonba-openapi/v2/client"
	client "github.com/aliyun/alibabacloud-bailian-go-sdk/client"
	"os"
)

func TestCreateTextEmbeddings() {
	accessKeyId := os.Getenv("ACCESS_KEY_ID")
	accessKeySecret := os.Getenv("ACCESS_KEY_SECRET")
	agentKey := os.Getenv("AGENT_KEY")
	endpoint := client.BroadscopeBailianPopEndpoint

	config := &openapi.Config{AccessKeyId: &accessKeyId,
		AccessKeySecret: &accessKeySecret,
		Endpoint:        &endpoint}

	openapiClient, err := apiClient.NewClient(config)
	if err != nil {
		fmt.Printf("failed to new client, err: %v\n", err)
		return
	}

	request := &apiClient.CreateTextEmbeddingsRequest{AgentKey: &agentKey}
	text := "今天天气怎么样"
	request.SetInput([]*string{&text})
	result, err := openapiClient.CreateTextEmbeddings(request)
	if err != nil {
		fmt.Printf("failed to create token, err: %v\n", err)
		return
	}

	resultBody := result.Body
	if !(*resultBody.Success) {
		requestId := resultBody.RequestId
		if requestId == nil {
			requestId = result.Headers["x-acs-request-id"]
		}

		errMessage := fmt.Sprintf("Failed to create embeddings, reason: %s RequestId: %s", *resultBody.Message, *requestId)
		fmt.Printf("%v\n", errMessage)
		return
	}

	embeddings := resultBody.Data.Embeddings
	if embeddings != nil {
		for _, embedding := range embeddings {
			fmt.Printf("index: %d, embeding : [", embedding.TextIndex)
			for _, num := range embedding.Embedding {
				fmt.Printf("%.16f, ", *num)
			}
			fmt.Printf("]")
		}
	}
}